Project

Olive - AI Nutrition Management

Groups

Nutritional assessment is an extremely important problem for every American. Studies suggest that as many as 90% of Americans fall short of Vitamins D&E as a result of their regular dietary habits, and up to 50% of Americans can’t get enough Vitamin A & Calcium.

This problem is even more prominent in less wealthy communities, where not only food budget is more limited, but education in basic nutritional facts also more lacking. Even if full records of daily food intake are available, knowledge about nutrients in foods is needed to reflect on recent food consumption and subsequently act to nutritionally complement recent habits.

Therefore, there are two major obstacles stopping many ordinary Americans from healthily managing their diets. The first is recording dietary intake, and the second is interpreting nutritional profiles from the foods you’re eating. It’s after these two steps that insight into nutritional intake can be inferred and insights into dietary balance can be made. We set out to drastically lower the efforts involved in both steps by utilizing machine learning technologies. Image recognition techno… View full description

Nutritional assessment is an extremely important problem for every American. Studies suggest that as many as 90% of Americans fall short of Vitamins D&E as a result of their regular dietary habits, and up to 50% of Americans can’t get enough Vitamin A & Calcium.

This problem is even more prominent in less wealthy communities, where not only food budget is more limited, but education in basic nutritional facts also more lacking. Even if full records of daily food intake are available, knowledge about nutrients in foods is needed to reflect on recent food consumption and subsequently act to nutritionally complement recent habits.

Therefore, there are two major obstacles stopping many ordinary Americans from healthily managing their diets. The first is recording dietary intake, and the second is interpreting nutritional profiles from the foods you’re eating. It’s after these two steps that insight into nutritional intake can be inferred and insights into dietary balance can be made. We set out to drastically lower the efforts involved in both steps by utilizing machine learning technologies. Image recognition technologies will be utilized to allow easy recording of dietary intake via photos, and nutrition data will be subsequently inferred based on USDA’s nutritional database, which also serves as the basis for nutritional evaluations from dietary records by nutritionists.

The result is a machine agent that can assist users to keep track of their dietary habits, and feedback nutritional deficiencies and suggestions to improve current diet to the user when needed.